Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A method for projective correction of an image containing at least one text portion that is distorted by perspective, the method comprising the steps of: image binarization, wherein said image is binarized; connected component analysis, wherein pixel blobs are detected in said at least one text portion of said binarized image and wherein for each of said pixel blobs a position determining pixel is selected on a pixel blob baseline of the pixel blob, said position determining pixel defining the position of the pixel blob in the binarized image; horizontal vanishing point determination, comprising the steps of: estimating text baselines by means of said position determining pixels of said pixel blobs, identifying horizontal vanishing point candidates from said estimated text baselines, and determining a horizontal vanishing point of said at least one text portion by means of said horizontal vanishing point candidates; vertical vanishing point determination, wherein a vertical vanishing point is determined for said at least one text portion on the basis of vertical features thereof; and projective correction, wherein said perspective in said image is corrected on the basis of said horizontal and vertical vanishing points; wherein said horizontal vanishing point determination comprises a first elimination step on the level of said position determining pixels, a second elimination step on the level of text baselines and a third elimination step on the level of horizontal vanishing point candidates.
A method corrects perspective distortions in images containing text. The method binarizes the image, then finds pixel "blobs" representing text characters using connected component analysis. For each blob, it selects a "position determining pixel" on the blob's baseline to represent the blob's location. It then estimates text baselines using these pixels and identifies candidate horizontal vanishing points. The actual horizontal vanishing point is determined from these candidates. A vertical vanishing point is found based on vertical features in the text. Finally, perspective correction is applied based on both vanishing points. During horizontal vanishing point determination, elimination steps are performed to refine the accuracy: first on the position determining pixels, second on the text baselines, and third on the vanishing point candidates.
2. The method according to claim 1 , wherein said position determining pixels are eigenpoints of said pixel blobs.
The method for projective correction of an image containing at least one text portion that is distorted by perspective, the method comprising the steps of: image binarization, wherein said image is binarized; connected component analysis, wherein pixel blobs are detected in said at least one text portion of said binarized image and wherein for each of said pixel blobs a position determining pixel is selected on a pixel blob baseline of the pixel blob, said position determining pixel defining the position of the pixel blob in the binarized image; horizontal vanishing point determination, comprising the steps of: estimating text baselines by means of said position determining pixels of said pixel blobs, identifying horizontal vanishing point candidates from said estimated text baselines, and determining a horizontal vanishing point of said at least one text portion by means of said horizontal vanishing point candidates; vertical vanishing point determination, wherein a vertical vanishing point is determined for said at least one text portion on the basis of vertical features thereof; and projective correction, wherein said perspective in said image is corrected on the basis of said horizontal and vertical vanishing points; wherein said horizontal vanishing point determination comprises a first elimination step on the level of said position determining pixels, a second elimination step on the level of text baselines and a third elimination step on the level of horizontal vanishing point candidates; wherein the "position determining pixels" used to represent each text blob are the "eigenpoints" of those blobs (mathematical points representing the blob's distribution).
3. The method according to claim 2 , wherein the first elimination step comprises the step of detecting confusing eigenpoints which are out of line with respect to eigenpoints in the vicinity of the eigenpoint in consideration and wherein said confusing eigenpoints are disregarded for said text baseline estimation.
The method for projective correction of an image containing at least one text portion that is distorted by perspective, the method comprising the steps of: image binarization, wherein said image is binarized; connected component analysis, wherein pixel blobs are detected in said at least one text portion of said binarized image and wherein for each of said pixel blobs eigenpoints are selected on a pixel blob baseline of the pixel blob, said eigenpoints defining the position of the pixel blob in the binarized image; horizontal vanishing point determination, comprising the steps of: estimating text baselines by means of said eigenpoints of said pixel blobs, identifying horizontal vanishing point candidates from said estimated text baselines, and determining a horizontal vanishing point of said at least one text portion by means of said horizontal vanishing point candidates; vertical vanishing point determination, wherein a vertical vanishing point is determined for said at least one text portion on the basis of vertical features thereof; and projective correction, wherein said perspective in said image is corrected on the basis of said horizontal and vertical vanishing points; wherein said horizontal vanishing point determination comprises a first elimination step on the level of said eigenpoints, a second elimination step on the level of text baselines and a third elimination step on the level of horizontal vanishing point candidates; the first elimination step detects and removes "confusing eigenpoints." These are eigenpoints that are misaligned with nearby eigenpoints, and are disregarded when estimating text baselines.
4. Method according to claim 3 , wherein said confusing eigenpoints are detected by means of the following steps: determining the width and height of the pixel blobs; determining mean values for width and height of the pixel blobs; and detecting said confusing eigenpoints as eigenpoints belonging to pixel blobs of which at least one of the width and height of the pixel blob in consideration differs by a predetermined extent from said calculated mean values.
The method for projective correction of an image containing at least one text portion that is distorted by perspective, the method comprising the steps of: image binarization, wherein said image is binarized; connected component analysis, wherein pixel blobs are detected in said at least one text portion of said binarized image and wherein for each of said pixel blobs eigenpoints are selected on a pixel blob baseline of the pixel blob, said eigenpoints defining the position of the pixel blob in the binarized image; horizontal vanishing point determination, comprising the steps of: estimating text baselines by means of said eigenpoints of said pixel blobs, identifying horizontal vanishing point candidates from said estimated text baselines, and determining a horizontal vanishing point of said at least one text portion by means of said horizontal vanishing point candidates; vertical vanishing point determination, wherein a vertical vanishing point is determined for said at least one text portion on the basis of vertical features thereof; and projective correction, wherein said perspective in said image is corrected on the basis of said horizontal and vertical vanishing points; wherein said horizontal vanishing point determination comprises a first elimination step on the level of said eigenpoints, a second elimination step on the level of text baselines and a third elimination step on the level of horizontal vanishing point candidates; confusing eigenpoints are detected by first measuring the width and height of each pixel blob and calculating average width and height values. Confusing eigenpoints are then identified as those belonging to pixel blobs whose width or height significantly deviates from these averages.
5. Method according to claim 2 , wherein said step of estimating text baselines comprises a step of clustering eigenpoints into eigenpoint groups, wherein said eigenpoint groups fulfil at least one of the following conditions: a point to point distance between the eigenpoints of the group is below a first distance threshold, a point to line distance between each eigenpoint of the group and a line formed by the eigenpoints of the group is below a second distance threshold, an off horizontal angle of the line formed by the eigenpoints of the group is below a maximum angle, and the eigenpoint group contains a minimum number of eigenpoints; and wherein said text baselines are estimated based on said eigenpoint groups.
The method for projective correction of an image containing at least one text portion that is distorted by perspective, the method comprising the steps of: image binarization, wherein said image is binarized; connected component analysis, wherein pixel blobs are detected in said at least one text portion of said binarized image and wherein for each of said pixel blobs eigenpoints are selected on a pixel blob baseline of the pixel blob, said eigenpoints defining the position of the pixel blob in the binarized image; horizontal vanishing point determination, comprising the steps of: estimating text baselines by means of said eigenpoints of said pixel blobs, identifying horizontal vanishing point candidates from said estimated text baselines, and determining a horizontal vanishing point of said at least one text portion by means of said horizontal vanishing point candidates; vertical vanishing point determination, wherein a vertical vanishing point is determined for said at least one text portion on the basis of vertical features thereof; and projective correction, wherein said perspective in said image is corrected on the basis of said horizontal and vertical vanishing points; wherein said horizontal vanishing point determination comprises a first elimination step on the level of said eigenpoints, a second elimination step on the level of text baselines and a third elimination step on the level of horizontal vanishing point candidates; Estimating text baselines involves clustering eigenpoints into groups. These groups meet at least one of these criteria: eigenpoints are close to each other, eigenpoints are close to a line formed by other eigenpoints in the group, the angle of the line formed by the eigenpoints is nearly horizontal, and the group contains a minimum number of eigenpoints. Text baselines are then estimated based on these eigenpoint groups.
6. Method according to claim 5 , wherein said first distance threshold, said second distance threshold, said maximum angle and said minimum number of eigenpoints are set adaptively based on content of the image.
The method for projective correction of an image containing at least one text portion that is distorted by perspective, the method comprising the steps of: image binarization, wherein said image is binarized; connected component analysis, wherein pixel blobs are detected in said at least one text portion of said binarized image and wherein for each of said pixel blobs eigenpoints are selected on a pixel blob baseline of the pixel blob, said eigenpoints defining the position of the pixel blob in the binarized image; horizontal vanishing point determination, comprising the steps of: estimating text baselines by means of said eigenpoints of said pixel blobs, identifying horizontal vanishing point candidates from said estimated text baselines, and determining a horizontal vanishing point of said at least one text portion by means of said horizontal vanishing point candidates; vertical vanishing point determination, wherein a vertical vanishing point is determined for said at least one text portion on the basis of vertical features thereof; and projective correction, wherein said perspective in said image is corrected on the basis of said horizontal and vertical vanishing points; wherein said horizontal vanishing point determination comprises a first elimination step on the level of said eigenpoints, a second elimination step on the level of text baselines and a third elimination step on the level of horizontal vanishing point candidates; The first distance threshold, the second distance threshold, the maximum angle and the minimum number of eigenpoints used in eigenpoint group clustering are set adaptively, based on the image content. Specifically, the thresholds are adjusted dynamically based on characteristics observed within the image itself, not fixed values.
7. Method according to claim 5 , wherein said step of estimating text baselines further comprises a step of eigenpoint group merging wherein eigenpoint groups on both sides of a disregarded eigenpoint are merged into a larger eigenpoint group.
The method for projective correction of an image containing at least one text portion that is distorted by perspective, the method comprising the steps of: image binarization, wherein said image is binarized; connected component analysis, wherein pixel blobs are detected in said at least one text portion of said binarized image and wherein for each of said pixel blobs eigenpoints are selected on a pixel blob baseline of the pixel blob, said eigenpoints defining the position of the pixel blob in the binarized image; horizontal vanishing point determination, comprising the steps of: estimating text baselines by means of said eigenpoints of said pixel blobs, identifying horizontal vanishing point candidates from said estimated text baselines, and determining a horizontal vanishing point of said at least one text portion by means of said horizontal vanishing point candidates; vertical vanishing point determination, wherein a vertical vanishing point is determined for said at least one text portion on the basis of vertical features thereof; and projective correction, wherein said perspective in said image is corrected on the basis of said horizontal and vertical vanishing points; wherein said horizontal vanishing point determination comprises a first elimination step on the level of said eigenpoints, a second elimination step on the level of text baselines and a third elimination step on the level of horizontal vanishing point candidates; The estimation of text baselines further includes a step where eigenpoint groups are merged. If an eigenpoint has been disregarded, and there are eigenpoint groups on both sides of this point, these groups are merged into a larger, combined group.
8. Method according to claim 1 , wherein the second elimination step comprises the steps of: assigning confidence levels to said text baselines, and eliminating text baselines on the basis of said confidence levels.
The method for projective correction of an image containing at least one text portion that is distorted by perspective, the method comprising the steps of: image binarization, wherein said image is binarized; connected component analysis, wherein pixel blobs are detected in said at least one text portion of said binarized image and wherein for each of said pixel blobs a position determining pixel is selected on a pixel blob baseline of the pixel blob, said position determining pixel defining the position of the pixel blob in the binarized image; horizontal vanishing point determination, comprising the steps of: estimating text baselines by means of said position determining pixels of said pixel blobs, identifying horizontal vanishing point candidates from said estimated text baselines, and determining a horizontal vanishing point of said at least one text portion by means of said horizontal vanishing point candidates; vertical vanishing point determination, wherein a vertical vanishing point is determined for said at least one text portion on the basis of vertical features thereof; and projective correction, wherein said perspective in said image is corrected on the basis of said horizontal and vertical vanishing points; wherein said horizontal vanishing point determination comprises a first elimination step on the level of said position determining pixels, a second elimination step on the level of text baselines and a third elimination step on the level of horizontal vanishing point candidates; In the second elimination step, confidence levels are assigned to each of the text baselines. Text baselines are then eliminated based on their assigned confidence levels; low confidence baselines are discarded.
9. Method according to claim 8 , wherein said confidence levels are determined on the basis of at least the length of the respective text baseline and the proximity of the group of eigenpoints used for estimating the text baseline and the resulting text baseline.
The method for projective correction of an image containing at least one text portion that is distorted by perspective, the method comprising the steps of: image binarization, wherein said image is binarized; connected component analysis, wherein pixel blobs are detected in said at least one text portion of said binarized image and wherein for each of said pixel blobs a position determining pixel is selected on a pixel blob baseline of the pixel blob, said position determining pixel defining the position of the pixel blob in the binarized image; horizontal vanishing point determination, comprising the steps of: estimating text baselines by means of said position determining pixels of said pixel blobs, identifying horizontal vanishing point candidates from said estimated text baselines, and determining a horizontal vanishing point of said at least one text portion by means of said horizontal vanishing point candidates; vertical vanishing point determination, wherein a vertical vanishing point is determined for said at least one text portion on the basis of vertical features thereof; and projective correction, wherein said perspective in said image is corrected on the basis of said horizontal and vertical vanishing points; wherein said horizontal vanishing point determination comprises a first elimination step on the level of said position determining pixels, a second elimination step on the level of text baselines and a third elimination step on the level of horizontal vanishing point candidates; The confidence levels assigned to text baselines are determined based on at least two factors: the length of the baseline, and how closely the group of eigenpoints used to estimate the baseline align with the resulting baseline. Long baselines with good eigenpoint alignment receive higher confidence.
10. Method according to claim 8 , wherein said elimination of text baselines is performed by means of a RANSAC algorithm in which said confidence levels are taken into account.
The method for projective correction of an image containing at least one text portion that is distorted by perspective, the method comprising the steps of: image binarization, wherein said image is binarized; connected component analysis, wherein pixel blobs are detected in said at least one text portion of said binarized image and wherein for each of said pixel blobs a position determining pixel is selected on a pixel blob baseline of the pixel blob, said position determining pixel defining the position of the pixel blob in the binarized image; horizontal vanishing point determination, comprising the steps of: estimating text baselines by means of said position determining pixels of said pixel blobs, identifying horizontal vanishing point candidates from said estimated text baselines, and determining a horizontal vanishing point of said at least one text portion by means of said horizontal vanishing point candidates; vertical vanishing point determination, wherein a vertical vanishing point is determined for said at least one text portion on the basis of vertical features thereof; and projective correction, wherein said perspective in said image is corrected on the basis of said horizontal and vertical vanishing points; wherein said horizontal vanishing point determination comprises a first elimination step on the level of said position determining pixels, a second elimination step on the level of text baselines and a third elimination step on the level of horizontal vanishing point candidates; Text baseline elimination is performed using a RANSAC (RANdom SAmple Consensus) algorithm. The confidence levels assigned to the text baselines are incorporated into the RANSAC process, influencing the selection of inliers and outliers, therefore lines with lower confidence levels are more likely to be outliers and discarded.
11. Method according to claim 1 , wherein the third elimination step comprises: performing projective correction on the basis of each identified horizontal vanishing point candidate; comparing the proximity of each horizontal vanishing point candidate to the resulting horizontal text direction after projective correction; and selecting the horizontal vanishing point candidate which is closest to the horizontal text direction of the image document after projective correction.
The method for projective correction of an image containing at least one text portion that is distorted by perspective, the method comprising the steps of: image binarization, wherein said image is binarized; connected component analysis, wherein pixel blobs are detected in said at least one text portion of said binarized image and wherein for each of said pixel blobs a position determining pixel is selected on a pixel blob baseline of the pixel blob, said position determining pixel defining the position of the pixel blob in the binarized image; horizontal vanishing point determination, comprising the steps of: estimating text baselines by means of said position determining pixels of said pixel blobs, identifying horizontal vanishing point candidates from said estimated text baselines, and determining a horizontal vanishing point of said at least one text portion by means of said horizontal vanishing point candidates; vertical vanishing point determination, wherein a vertical vanishing point is determined for said at least one text portion on the basis of vertical features thereof; and projective correction, wherein said perspective in said image is corrected on the basis of said horizontal and vertical vanishing points; wherein said horizontal vanishing point determination comprises a first elimination step on the level of said position determining pixels, a second elimination step on the level of text baselines and a third elimination step on the level of horizontal vanishing point candidates; In the third elimination step, projective correction is performed using each candidate horizontal vanishing point. The proximity of each vanishing point candidate to the horizontal text direction after correction is compared. The candidate closest to the horizontal text direction after correction is selected as the final horizontal vanishing point.
12. Method according to claim 1 , wherein a first and a second horizontal vanishing point candidate are estimated from said text baselines after said second elimination step and wherein for said estimation of said first and second horizontal vanishing point candidates different approximation methods are used, chosen from the group consisting of: a least squares method, a weighted least squares method and an adaptive least squares method.
The method for projective correction of an image containing at least one text portion that is distorted by perspective, the method comprising the steps of: image binarization, wherein said image is binarized; connected component analysis, wherein pixel blobs are detected in said at least one text portion of said binarized image and wherein for each of said pixel blobs a position determining pixel is selected on a pixel blob baseline of the pixel blob, said position determining pixel defining the position of the pixel blob in the binarized image; horizontal vanishing point determination, comprising the steps of: estimating text baselines by means of said position determining pixels of said pixel blobs, identifying horizontal vanishing point candidates from said estimated text baselines, and determining a horizontal vanishing point of said at least one text portion by means of said horizontal vanishing point candidates; vertical vanishing point determination, wherein a vertical vanishing point is determined for said at least one text portion on the basis of vertical features thereof; and projective correction, wherein said perspective in said image is corrected on the basis of said horizontal and vertical vanishing points; wherein said horizontal vanishing point determination comprises a first elimination step on the level of said position determining pixels, a second elimination step on the level of text baselines and a third elimination step on the level of horizontal vanishing point candidates; After the second elimination step, two horizontal vanishing point candidates are estimated from the text baselines. The first candidate uses one approximation method, and the second candidate uses a different approximation method, selected from least squares, weighted least squares, and adaptive least squares. This allows for testing different methods and then selecting the best vanishing point based on other criteria in the claims.
13. The method according to claim 1 , wherein a step of text and picture separation is performed after said image binarization and before said connected component analyses, and only textual information is kept in said binarized image.
The method for projective correction of an image containing at least one text portion that is distorted by perspective, the method comprising the steps of: image binarization, wherein said image is binarized; connected component analysis, wherein pixel blobs are detected in said at least one text portion of said binarized image and wherein for each of said pixel blobs a position determining pixel is selected on a pixel blob baseline of the pixel blob, said position determining pixel defining the position of the pixel blob in the binarized image; horizontal vanishing point determination, comprising the steps of: estimating text baselines by means of said position determining pixels of said pixel blobs, identifying horizontal vanishing point candidates from said estimated text baselines, and determining a horizontal vanishing point of said at least one text portion by means of said horizontal vanishing point candidates; vertical vanishing point determination, wherein a vertical vanishing point is determined for said at least one text portion on the basis of vertical features thereof; and projective correction, wherein said perspective in said image is corrected on the basis of said horizontal and vertical vanishing points; wherein said horizontal vanishing point determination comprises a first elimination step on the level of said position determining pixels, a second elimination step on the level of text baselines and a third elimination step on the level of horizontal vanishing point candidates; A step of separating text and picture elements is performed after the image binarization and before the connected component analysis. This ensures that only the textual information is kept in the binarized image, removing any non-textual elements that might interfere with the text analysis and perspective correction.
14. A system for projective correction of an image containing at least one text portion that is distorted by perspective, the system comprising at least one processor and an associated storage containing a program executable by means of said at least one processor and comprising: first software code portions configured for image binarization, which when executed binarize said image; second software code portions configured for connected component analysis, which when executed detect pixel blobs in said at least one text portion of said binarized image and wherein for each of said pixel blobs a position determining pixel is selected on a pixel blob baseline of the pixel blob, said position determining pixel defining the position of the pixel blob in the binarized image; third software code portions configured for horizontal vanishing point determination, which when executed perform the steps of: estimating text baselines by means of said position determining pixels of said pixel blobs, identifying horizontal vanishing point candidates from said estimated text baselines, and determining a horizontal vanishing point of said at least one text portion by means of said horizontal vanishing point candidates; fourth software code portions configured for vertical vanishing point determination, which when executed determine a vertical vanishing point for said at least one text portion on the basis of vertical features thereof; and fifth software code portions for projective correction, which when executed correct said perspective in said image on the basis of said horizontal and vertical vanishing points; wherein said third software code portions when executed perform a first elimination step on the level of said position determining pixels, a second elimination step on the level of text baselines and a third elimination step on the level of horizontal vanishing point candidates.
A system corrects perspective distortions in images containing text. It includes a processor and storage with a program that binarizes the image, then finds pixel "blobs" representing text characters using connected component analysis. For each blob, it selects a "position determining pixel" on the blob's baseline to represent the blob's location. It then estimates text baselines using these pixels and identifies candidate horizontal vanishing points. The actual horizontal vanishing point is determined from these candidates. A vertical vanishing point is found based on vertical features in the text. Finally, perspective correction is applied based on both vanishing points. During horizontal vanishing point determination, elimination steps are performed to refine the accuracy: first on the position determining pixels, second on the text baselines, and third on the vanishing point candidates.
15. The system of claim 14 , comprising one of the following: a personal computer, a portable computer, a laptop computer, a netbook computer, a tablet computer, a smartphone, a digital still camera, a video camera, a mobile communication device, a personal digital assistant, a scanner, a multi-function device.
The invention relates to a system for processing and managing digital content, particularly in computing and multimedia devices. The system addresses the need for efficient handling of digital data, such as images, videos, and documents, across various electronic devices. The core functionality involves capturing, storing, and manipulating digital content with enhanced performance and user interaction capabilities. The system includes a processing unit configured to execute instructions for content management, a memory module for storing data and software, and an input/output interface for interfacing with peripheral devices. Additionally, the system may incorporate specialized hardware or software modules to optimize tasks such as image processing, video encoding, or document scanning. The system is designed to operate on a range of computing platforms, including personal computers, portable computers, laptops, netbooks, tablet computers, smartphones, digital cameras, video cameras, mobile communication devices, personal digital assistants, scanners, and multi-function devices. This versatility ensures compatibility with diverse user needs and applications, from professional multimedia editing to everyday document management. The system enhances productivity by streamlining workflows and improving the efficiency of digital content handling across different devices.
16. A non-transient storage medium on which a computer program product is stored comprising software code portions in a format executable on a computer device and configured for performing the following steps when executed on said computer device: image binarization, wherein said image is binarized; connected component analysis, wherein pixel blobs are detected in said at least one text portion of said binarized image and wherein for each of said pixel blobs a position determining pixel is selected on a pixel blob baseline of the pixel blob, said position determining pixel defining the position of the pixel blob in the binarized image; horizontal vanishing point determination, comprising the steps of: estimating text baselines by means of said position determining pixels of said pixel blobs, identifying horizontal vanishing point candidates from said estimated text baselines, and determining a horizontal vanishing point of said at least one text portion by means of said horizontal vanishing point candidates; vertical vanishing point determination, wherein a vertical vanishing point is determined for said at least one text portion on the basis of vertical features thereof; and projective correction, wherein said perspective in said image is corrected on the basis of said horizontal and vertical vanishing points; wherein said horizontal vanishing point determination comprises a first elimination step on the level of said position determining pixels, a second elimination step on the level of text baselines and a third elimination step on the level of horizontal vanishing point candidates.
A non-transient storage medium stores a program that corrects perspective distortions in images containing text. The program binarizes the image, then finds pixel "blobs" representing text characters using connected component analysis. For each blob, it selects a "position determining pixel" on the blob's baseline to represent the blob's location. It then estimates text baselines using these pixels and identifies candidate horizontal vanishing points. The actual horizontal vanishing point is determined from these candidates. A vertical vanishing point is found based on vertical features in the text. Finally, perspective correction is applied based on both vanishing points. During horizontal vanishing point determination, elimination steps are performed to refine the accuracy: first on the position determining pixels, second on the text baselines, and third on the vanishing point candidates.
Unknown
August 19, 2014
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.